Format Inertia: A Failure Mechanism of LLMs in Medical Pre-Consultation
This addresses a failure mechanism in LLMs for medical pre-consultation, which is incremental as it builds on existing SFT methods.
The paper tackles the problem of LLMs generating repetitive and uninformative questions in medical pre-consultation dialogues due to skewed turn-count distributions in training data, and shows that rebalancing the dataset substantially alleviates this issue.
Recent advances in Large Language Models (LLMs) have brought significant improvements to various service domains, including chatbots and medical pre-consultation applications. In the healthcare domain, the most common approach for adapting LLMs to multi-turn dialogue generation is Supervised Fine-Tuning (SFT). However, datasets for SFT in tasks like medical pre-consultation typically exhibit a skewed turn-count distribution. Training on such data induces a novel failure mechanism we term Format Inertia, where models tend to generate repetitive, format-correct, but diagnostically uninformative questions in long medical dialogues. To mitigate this observed failure mechanism, we adopt a simple, data-centric method that rebalances the turn-count distribution of the training dataset. Experimental results show that our approach substantially alleviates Format Inertia in medical pre-consultation.